★ 600A meta-skill that produces skills. Point it at any codebase and it distills the project's rules, workflows, and hard-won lessons into a dedicated skills/<name>/ directory — a project skill that becomes the single source of truth every AI agent (Cursor, Claude Code, Codex, Windsurf, Gemini) consults before every task.
Shell49 forks
★ 575用 ChatGPT/Codex 安裝 AI 剪輯環境,並依八大步驟完成可驗證的短影音剪輯。
Shell92 forks
★ 568Use your NVIDIA GPU's VRAM as swap space on Linux. Built for laptops with soldered memory and no upgrade path. If you have an RTX card sitting there with 8GB of VRAM and you're getting swapped to SSD, this puts that VRAM to work
Shell17 forks
★ 558OpenClaw-inspired autonomous AI agent built entirely in n8n. Adaptive RAG-powered memory, Skills via MCP templates, Expert Agents with delegated sub-agents, proactive task management, media understanding - self-hosted with one setup script
Shell104 forks
★ 553Spec-driven development with smart compaction. Claude Code plugin combining Ralph Wiggum loop with structured specification workflow.
Shell49 forks
★ 548The complete guide to Claude Code: CLAUDE.md, hooks, skills, MCP servers, and commands
Shell48 forks
★ 542200+ production open source Rails apps & engines in one repo. Search across real codebases with AI agents to research architectural patterns.
Shell27 forks
★ 541AI agent skills for social media content strategy, creation, and analysis across text-first platforms
Shell89 forks
★ 532🤖 AI social-media automation skill | Self-evolution workflows | AI 社交媒体自动化 skill | 自我进化工作流
Shell79 forks
★ 531EnvKit — free local development environment for Windows & macOS: nginx/Apache, multiple PHP versions, MySQL/MariaDB, PostgreSQL, Redis, MongoDB, Mailpit, Node.js, trusted .test HTTPS, and a built-in MCP server for AI-assistant control. A Laragon/XAMPP/Herd alternative.
Shell18 forks
★ 515Save tokens. Maximize context, Safely
Shell23 forks
★ 514MCP server SDK/example implemented entirely in bash — build a Model Context Protocol server with no runtime dependency beyond a POSIX shell.
Shell48 forks
★ 511⚡️ A curated library of Agent Skills focused on Jetpack Compose performance.
Shell19 forks
★ 497Openclaw多智能体协同系统 | Multi-Agent OS for Decision Makers — 基于 OpenClaw (Clawbot) + Slack,让 AI 团队各司其职、自主稳定迭代。
Shell71 forks
★ 491Huge AI models catalog. A curated list of AI tools, platforms, and resources across various domains.
Shell85 forks
★ 480Best practices, reference architectures, and examples for distributed AI training and inference on AWS.
Shell207 forks

shangsitongshizaitiantang ★ 477 为中国 industry 求职者打造的简历方法论 toolkit / Industry resume methodology for Chinese job seekers
Shell11 forks
★ 472Always-on token-efficiency skill for coding agents (Claude Code, Codex, Cursor, Windsurf, Cline). ~31% lower bill on average, no loss of correctness.
Shell4 forks
★ 472Fuse two frontier models into one Fable-tier answer: Opus 4.8 drafts, a second model (Opus 4.8 or GPT-5.5 via codex) checks, Opus fuses. A Claude Code skill.
Shell74 forks
★ 471Three-layer audit enforcement framework for AI agents — hooks, skills, context recovery, and audit-driven daily reports
Shell3 forks